Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _die
    -0.07
     Ан
    -0.07
    rosse
    -0.07
    _partitions
    -0.07
     одна
    -0.07
    poň
    -0.07
     alone
    -0.06
     zijn
    -0.06
    計
    -0.06
     Όμιλος
    -0.06
    POSITIVE LOGITS
    —you
    0.07
    —we
    0.06
    ToWorld
    0.06
    							↵
    0.06
    _FIND
    0.06
    Clear
    0.06
    ＿＿＿＿＿＿＿＿
    0.06
    ,end
    0.06
     ham
    0.06
     tracked
    0.06
    Act Density 0.057%

    No Known Activations